Cost-Sensitive ROI Detection Method for Medical Images Based on Cascade Architecture
LI Ning,GUO Qiao-Jin,XIE Jun-Yuan,CHEN Shi-Fu
State Key Laboratory for Novel Software Technology,Nanjing University,Nanjing 210093 Department of Computer Science and Technology,Nanjing University,Nanjing 210093
Abstract Regions of Interest (ROI) in medical images contain important information and are of great significance to the analysis and diagnosis. A cost-sensitive ROI detection method for medical images based on Cascade architecture is proposed in this paper, which combines the characters of medical images and applies machine learning and image process. This method achieves high sensitivity and efficiency by effectively integrating cost-sensitive classifier method and Cascade architecture. Experimental results on mammograms show that the method is more efficient and less in calculated amount than pixel-based methods, meanwhile avoids the difficulty of detecting masses by using traditional segmentation and filtering techniques with region-based approach.
[1] Bazzocchi M, Mazzarella F, Del Frate C, et al. CAD Systems for Mammography: A Real Opportunity? A Review of the Literature. La Radiologia Medica, 2007, 112(3): 329-353 [2] Sluimer I, Schilham A, Prokop M, et al. Computer Analysis of Computed Tomography Scans of the Lung: A Survey. IEEE Trans on Medical Imaging, 2006, 25(4): 385-405 [3] Viola P, Jones M J. Robust Real-Time Face Detection. International Journal of Computer Vision, 2004, 57(2): 137-154 [4] Domingos P. Metacost: A General Method for Making Classifiers Cost-Sensitive // Proc of the 5th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Diego, USA, 1999: 155-164
[5] Lee W, Fan W, Stolfo S J, et al. Cost-Sensitive Modeling for Intrusion Detection // Maloof M A, ed. Machine Learning and Data Mining for Computer Security: Methods and Applications. New York, USA: Springer-Verlag, 2006: 125-136 [6] Long Jun, Yin Jianping, Zhu En, et al. A Novel Active Cost-Sensitive Learning Method for Intrusion Detection // Proc of the International Conference on Machine Learning and Cybernetics. Kunming, China, 2008, Ⅱ: 1099-1104 [7] Kononenko I. Estimating Attributes: Analysis and Extensions of RELIEF // Proc of the European Conference on Machine Learning. Catania, Italy, 1994: 171-182 [8] Yu Lei, Liu Huan. Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution // Proc of the 12th International Conference on Machine Learning. Washington, USA, 2003: 856-863 [9] Kohavi R, John G H. Wrappers for Feature Subset Selection. Artificial Intelligence, 1997, 97(1/2): 273-324 [10]Robnikikonja M, Kononenko I. Theoretical and Empirical Analysis of ReliefF and RReliefF. Machine Learning, 2003, 53(1/2): 23-69 [11] Evans W P. Breast Masses, Appropriate Evaluation. Radiologic Clinics of North America, 1995, 33(6): 1085-1088 [12] Gori I, Retico A. A Pixel-Based Approach to Massive Lesion Detection in X-Ray Mammography [EB/OL]. [2009-06-30]. http://arxiv.org/ftp/physics/papers/05710507152.pdf [13] Fauci F, Bagnasco S, Bellotti R, et al. Mammogram Segmentation by Contour Searching and Massive Lesion Classification with Neural Network // Proc of the IEEE Nuclear Science Symposium Conference Record. Rome, Italy, 2004, Ⅴ: 2695-2699 [14] Yang S C, Wang C M, Chung Y N, et al. A Computer-Aided System for Mass Detection and Classification in Digitized Mammograms. Biomedical Engineering Applications Basis Communications, 2005, 17(5): 215-228 [15] Ojala T, Pietikainen M, Harwood D. A Comparative Study of Texture Measures with Classification Based on Featured Distributions. Pattern Recognition, 1996, 29(1): 51-59 [16] Ojala T, Pietikainen M, Maenpaa T. Multiresolution Gray-Scale and Rotation Invariant Textureclassification with Local Binary Patterns. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987
2010, Vol. 23 
